@article{405, author = "Yilei Xu", abstract = "ESG (Environmental, Social and Governance) is a prominent investment approach that aims to generate excess returns by incorporating information on the E, S, and G dimensions of a company into an equity portfolio. As compared to traditional financial performance-focused investment concepts, ESG investing places greater emphasis on the social responsibility undertaken by companies, and has gained significant attention from governments and investors. As a result, many domestic and international rating agencies have introduced ESG indicators and applied them in practice, leading to a gradual expansion of the domestic and international ESG investment management market, which has gradually become the new mainstream of international investment. Research on ESG investment has become a top priority, however, relevant domestic research is still in its infancy. Therefore, it is essential to study investment strategies based on ESG factors. In this paper, we propose a neural network prediction model based on ESG investment. The model uses ESG rating data of mutual funds and ETFs from 2010 to 2020, to investigate the impact of adding ESG-related factors on the returns of these two types of funds, and to compare the impact on them. The results of the study indicate that fund returns can be more accurately predicted by adding ESG data and that ESG data is more applicable to mutual fund return forecasting. This suggests that ESG factors, as an alternative data source that has not been over-explored, can compensate for the shortcomings of traditional investment strategies through the introduction of alternative information and thus achieve higher returns. In summary, this study contributes to the literature on ESG investment strategies by proposing a novel neural network prediction model and demonstrating the potential benefits of incorporating ESG data into investment decisions. The findings have important implications for investors, fund managers, and policymakers, and suggest the need for further research on the effectiveness of ESG investment strategies.", issn = "23942894", journal = "IJASM", keywords = "Fund Return Forecasting;Investment Strategy Design;ESG Factors;Neural Networks", month = "May", number = "3", pages = "26-31", title = "{F}und {R}eturn {F}orecasting based on {ESG} {F}actors", volume = "10", year = "2023", }